Linearity of Age at Cancer Onset Worldwide: 25-Year Population-Based Cancer Registry Study

Simple Summary: The age at cancer onset varies worldwide and is intuitively linked to the age structure of the population originating the cases. The exact amount by which age explains this pattern has been estimated for breast cancer to give clues about the 10-year difference in age at cancer onset between low/middle and high income countries. The age contribution for 20 selected cancer types was calculated, using cancer incidence data from all worldwide cancer registries, through linear regression models. For all cancers but skin, age explained 56% of the pattern in men and 65% in women. The percentages varied by cancer types. Since age at cancer onset is embedded with the age structure of the underlying population, it is possible to avoid misinterpretations of a high frequency of cancer onset in specific age groups by inspecting the age pyramid of the population to check for the plausibility of the excess.Background The linear association between median age at cancer onset and median age of the underlying population has been described only for breast cancer. We quantified the shape and strength of such association for 20 cancer types using data from all population-based cancer registries (CRs) worldwide. Methods The patients' median age at cancer onset and of the underlying population were extracted from all CRs listed in volumes VI (1983-1987 years) and XI (2008-2012 years) of Cancer Incidence in Five Continents. The association was assessed at cross-sectional level by linear regression models and longitudinally considering only the long-standing CRs active throughout the study period (i.e., 25-year span). Results During 2008-2012, each one-year increase in median population ageing was associated in men with a nearly half year increase of median age at onset of all cancers, but skin; and a 2/3 year increase in women. Variance explained by linear model was around 60%. In long-standing CRs a decrease in median age at cancer onset was observed for prostate and cervical cancers throughout the 25-year span. Conclusions Population ageing reflected 60% of the median age at cancer onset. Misinterpretation of peaks of cancer incidence in specific age groups may be avoided by examining population pyramids.